When an analysis is conducted using variables in multiple data files, Q needs to work out how the observations in the data files relate to each other. This allows users to crosstab questions from two different data files, provided those files have a data file relationship that tells Q how the observations relate to each other. The link connects common respondents/observations in both data sets together so if you want to analyze them, the appropriate value(s) from each data set lines up for the corresponding observations.
Linking data sets is commonly done when you have unstacked data and want to analyze it against stacked data from the same survey, or when you have related data from two different data sources. However, this should not be used as a substitution to merging in new variables into your data, see Method 2 Merging in new variables, nor will it work for analyzing wave on wave data, see Method 1 Merging in new cases. There are also some limitations to working with variables across data sets: 1) they cannot be used in the same banner and 2) filters created can only apply to an output that uses data from same data set as the filter.
- Two different data files loaded in Q.
- There must be a variable in each file that contains the same type of data (text, categorical, dates, etc.) and has some values that match.
Data file relationships can be edited by selecting File > Data Sets > Edit Relationships.
This window shows a list of any existing data file relationships. In order to crosstab questions from two different data files, those two data files must have a relationship that appears in this list.
To see more detail about an existing relationship, select it in the list, and then click Edit to view the Data Set Relationship details:
You can also remove an existing relationship by selecting it from the list, and then clicking Delete.
To create a new relationship, click the New Relationship button.